Early warning diagnosis method of engine temperature fault of wind turbine generator

Abstract

The invention relates to the field of new-energy wind power generation system, particularly to an early warning diagnosis method of the engine temperature fault of a wind turbine generator. The methodcomprises: step one, determining parameters related to an early warning part of a wind turbine generator among historical data of a wind farm; step two, training a neural network by using the historical data of the related parameters to obtain a real-time theoretical temperature normal value of the wind turbine generator; step three, acquiring real-time data of the related parameters; and step four, according to the real-time theoretical temperature normal value, a preset temperature fault criterion threshold, and the real-time data, determining whether the wind turbine generator has an engine temperature fault. Therefore, the conflict between the early warning time of the engine temperature fault of the wind turbine generator and the fault early-warning precision is eliminated effectively; and the diagnosis accuracy and the diagnosis time lead are improved obviously.

Description

technical field [0001] The invention relates to the field of new energy wind power generation systems, in particular to a temperature warning and diagnosis method for a wind turbine generator. Background technique [0002] As a green and non-polluting new energy, wind energy has been paid more and more attention, and it may become the main energy resource of human beings in the future. Affected by complex and changeable environmental factors, the performance of each component of the wind turbine will gradually decline during operation, which will eventually lead to component failure. The fault warning of wind turbine components can detect hidden dangers in advance, which is conducive to optimizing maintenance plans and avoiding more serious machine failures caused by component failures. [0003] Fan data acquisition and monitoring (SCADA, Supervisory Control and Data Acquisition) system, as an important part of fan status monitoring, can provide data for monitoring fan stat...

AI Technical Summary

Problems solved by technology

Due to the correlation between the SCADA parameters of wind farms, the method of using parameter correlation to select the input parameters of the neural network has the problem of repeated use of parameters and data redundancy when the input parameters are highly correlated.

However, the input parameters of the neural network are selected through the subjective experience method. Since there are many parameters affecting the fan components, the selected parameters are inaccurate, resulting in low efficiency of the neural network, too few selected parameters, and insufficient accuracy.

Images